No abstract

Neural architecture search (NAS) has witnessed prevailing success in image classification and (very recently) segmentation tasks. In this paper, we present the first preliminary study on introducing the NAS algorithm to generative adversarial networks (GANs), dubbed AutoGAN. The marriage of NAS and GANs faces its unique challenges. We define the search space for the generator architectural variations and use an RNN controller to guide the search, with parameter sharing and dynamic-resetting to accelerate the process. Inception score is adopted as the reward, and a multi-level search strategy is introduced to perform NAS in a progressive way. Experiments validate the effectiveness of AutoGAN on the task of unconditional image generation. Specifically, our discovered architectures achieve highly competitive performance compared to current stateof-the-art hand-crafted GANs, e.g., setting new state-of-theart FID scores of 12.42 on CIFAR-10, and 31.01 on STL-10, respectively. We also conclude with a discussion of the current limitations and future potential of AutoGAN. The code is avaliable at https://github.com/TAMU-VITA/ AutoGAN .• We use Inception score (IS) [50] as the reward, in the reinforcement-learning-based optimization of Au-toGAN. The discovered models are found also to show

No abstract

Figure 1: Representative visual examples by enhancing low-light images using EnlightenGAN.

Materials capable of extracting gold from complex sources, especially electronic waste (e-waste), are needed for gold resource sustainability and effective e-waste recycling. However, it remains challenging to achieve high extraction capacity and precise selectivity if only a trace amount of gold is present along with other metallic elements . Here we report an approach based on reduced graphene oxide (rGO) which provides an ultrahigh capacity and selective extraction of gold ions present in ppm concentrations (>1000 mg of gold per gram of rGO at 1 ppm). The excellent gold extraction performance is accounted to the graphene areas and oxidized regions of rGO. The graphene areas spontaneously reduce gold ions to metallic gold, and the oxidized regions allow good dispersibility of the rGO material so that efficient adsorption and reduction of gold ions at the graphene areas can be realized. By controlling the protonation of the oxidized regions of rGO, gold can be extracted exclusively, without contamination by the other 14 co-existing elements typically present in e-waste. These findings are further exploited to demonstrate recycling gold from real-world e-waste with good scalability and economic viability, as exemplified by using rGO membranes in a continuous flow-through process.